Index: lib/CodeGen/BranchFolding.cpp
===================================================================
--- lib/CodeGen/BranchFolding.cpp
+++ lib/CodeGen/BranchFolding.cpp
@@ -388,7 +388,7 @@
   NewMBB->splice(NewMBB->end(), &CurMBB, BBI1, CurMBB.end());
 
   // NewMBB belongs to the same loop as CurMBB.
-  if (MLI) 
+  if (MLI)
     if (MachineLoop *ML = MLI->getLoopFor(&CurMBB))
       ML->addBasicBlockToLoop(NewMBB, MLI->getBase());
 
@@ -426,6 +426,15 @@
   return Time;
 }
 
+/// getBranchDebugLoc - Find and return, if any, the DebugLoc of the branch
+/// instructions on the block.
+static DebugLoc getBranchDebugLoc(MachineBasicBlock &MBB) {
+  MachineBasicBlock::iterator I = MBB.getLastNonDebugInstr();
+  if (I != MBB.end() && I->isBranch())
+    return I->getDebugLoc();
+  return DebugLoc();
+}
+
 // CurMBB needs to add an unconditional branch to SuccMBB (we removed these
 // branches temporarily for tail merging).  In the case where CurMBB ends
 // with a conditional branch to the next block, optimize by reversing the
@@ -436,7 +445,7 @@
   MachineFunction::iterator I = std::next(MachineFunction::iterator(CurMBB));
   MachineBasicBlock *TBB = nullptr, *FBB = nullptr;
   SmallVector<MachineOperand, 4> Cond;
-  DebugLoc dl;  // FIXME: this is nowhere
+  DebugLoc dl = getBranchDebugLoc(*CurMBB);
   if (I != MF->end() && !TII->analyzeBranch(*CurMBB, TBB, FBB, Cond, true)) {
     MachineBasicBlock *NextBB = &*I;
     if (TBB == NextBB && !Cond.empty() && !FBB) {
@@ -1050,7 +1059,7 @@
 
         // Remove the unconditional branch at the end, if any.
         if (TBB && (Cond.empty() || FBB)) {
-          DebugLoc dl;  // FIXME: this is nowhere
+          DebugLoc dl = getBranchDebugLoc(*PBB);
           TII->removeBranch(*PBB);
           if (!Cond.empty())
             // reinsert conditional branch only, for now
@@ -1191,15 +1200,6 @@
   return MBB2I->isCall() && !MBB1I->isCall();
 }
 
-/// getBranchDebugLoc - Find and return, if any, the DebugLoc of the branch
-/// instructions on the block.
-static DebugLoc getBranchDebugLoc(MachineBasicBlock &MBB) {
-  MachineBasicBlock::iterator I = MBB.getLastNonDebugInstr();
-  if (I != MBB.end() && I->isBranch())
-    return I->getDebugLoc();
-  return DebugLoc();
-}
-
 /// OptimizeBlock - Analyze and optimize control flow related to the specified
 /// block.  This is never called on the entry block.
 bool BranchFolder::OptimizeBlock(MachineBasicBlock *MBB) {
Index: test/CodeGen/X86/branchfolding-debugloc.ll
===================================================================
--- /dev/null
+++ test/CodeGen/X86/branchfolding-debugloc.ll
@@ -0,0 +1,83 @@
+; RUN: llc < %s | FileCheck %s
+;
+; The test code is generated from the following source code:
+; 
+;  1 extern int bar(int x);
+;  2
+;  3 int foo(int *begin, int *end) {
+;  4   int *i;
+;  5   int ret = 0;
+;  6   for (
+;  7       i = begin ;
+;  8       i != end ;
+;  9       i++)
+; 10   {
+; 11       ret += bar(*i);
+; 12   }
+; 13   return ret;
+; 14 }
+; 
+; CHECK: # %entry
+; CHECK-NOT: # %for.body
+; CHECK: .loc  1 6 3
+; CHECK-NEXT: je  [[BB:.LBB[^ ]+]]
+; CHECK: [[BB]]:{{.}}# %for.end
+
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @foo(i32* readonly %begin, i32* readnone %end) !dbg !4 {
+entry:
+  %cmp6 = icmp eq i32* %begin, %end, !dbg !9
+  br i1 %cmp6, label %for.end, label %for.body.preheader, !dbg !12
+
+for.body.preheader:                               ; preds = %entry
+  br label %for.body, !dbg !13
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %ret.08 = phi i32 [ %add, %for.body ], [ 0, %for.body.preheader ]
+  %i.07 = phi i32* [ %incdec.ptr, %for.body ], [ %begin, %for.body.preheader ]
+  %0 = load i32, i32* %i.07, align 4, !dbg !13, !tbaa !15
+  %call = tail call i32 @bar(i32 %0), !dbg !19
+  %add = add nsw i32 %call, %ret.08, !dbg !20
+  %incdec.ptr = getelementptr inbounds i32, i32* %i.07, i64 1, !dbg !21
+  %cmp = icmp eq i32* %incdec.ptr, %end, !dbg !9
+  br i1 %cmp, label %for.end.loopexit, label %for.body, !dbg !12, !llvm.loop !22
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end, !dbg !24
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  %ret.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.end.loopexit ]
+  ret i32 %ret.0.lcssa, !dbg !24
+}
+
+declare i32 @bar(i32)
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2, !3}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, emissionKind: FullDebug)
+!1 = !DIFile(filename: "foo.c", directory: "b/")
+!2 = !{i32 2, !"Dwarf Version", i32 4}
+!3 = !{i32 2, !"Debug Info Version", i32 3}
+!4 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 3, type: !5, isLocal: false, isDefinition: true, scopeLine: 3, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!5 = !DISubroutineType(types: !6)
+!6 = !{!7, !8, !8}
+!7 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!8 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !7, size: 64)
+!9 = !DILocation(line: 8, column: 9, scope: !10)
+!10 = distinct !DILexicalBlock(scope: !11, file: !1, line: 6, column: 3)
+!11 = distinct !DILexicalBlock(scope: !4, file: !1, line: 6, column: 3)
+!12 = !DILocation(line: 6, column: 3, scope: !11)
+!13 = !DILocation(line: 11, column: 18, scope: !14)
+!14 = distinct !DILexicalBlock(scope: !10, file: !1, line: 10, column: 3)
+!15 = !{!16, !16, i64 0}
+!16 = !{!"int", !17, i64 0}
+!17 = !{!"omnipotent char", !18, i64 0}
+!18 = !{!"Simple C/C++ TBAA"}
+!19 = !DILocation(line: 11, column: 14, scope: !14)
+!20 = !DILocation(line: 11, column: 11, scope: !14)
+!21 = !DILocation(line: 9, column: 8, scope: !10)
+!22 = distinct !{!22, !12, !23}
+!23 = !DILocation(line: 12, column: 3, scope: !11)
+!24 = !DILocation(line: 13, column: 3, scope: !4)